Low-Cost Monitoring Technologies for Detecting Pregnancy Complications and Facilitating Timely Interventions in Low-Resource Settings

In this project, we focus on building AI models for real-time processing of fetal cardiac activity and detecting pregnancy complications. We are collaborating with Emory Co-Design Lab and a Guatemalan NGO, Wuqu' Kawoq, to support community healthcare workers and improve outcomes in pregnancy and early childhood.

Related Publications

• Ramos, E., Palax, I.P., Cuxil, E.S., Iquic, E.S., Ajqui, A.C., Miller, A.C., Chandrasekeran, S., Hall-Clifford, R., Sameni, R., Katebi, N. and Clifford, G.D., 2024. Mobil Monitoring Doppler Ultrasound (MoMDUS) study: protocol for a prospective, observational study investigating the use of artificial intelligence and low-cost Doppler ultrasound for the automated quantification of hypertension, pre-eclampsia and fetal growth restriction in rural Guatemala. BMJ open, 14(9), p.e090503. Link
• Katebi, N., Sameni, R., Rohloff, P. and Clifford, G.D., 2023. Hierarchical attentive network for gestational age estimation in low-resource settings. IEEE journal of biomedical and health informatics, 27(5), pp.2501-2511. Link
• Katebi, N., Sameni, R. and Clifford, G.D., 2020. Deep Sequence Learning for Accurate Gestational Age Estimation from a $25 Doppler Device. arXiv preprint arXiv:2012.00553. Link